Export what a legal hold keeps as a ZIP (LH-12)

inbuxa:HoldExport/set takes a hold, optionally some of the accounts it
covers, and a reason; the collection runs in the background and get
says when it's ready. The ZIP has, per account, mail as .eml under its
folders, calendars as .ics, contacts as .vcf, files as stored, and the
archived items the hold keeps under archived/; a manifest.csv gives each
entry's account, kind, folder, date, whether it was archived, size and
SHA-256, and manifest.sha256 hashes the manifest. Accounts the hold
doesn't cover are left out, and items outside its date range are too:
live mail by arrival, events by start, and archived items the same way,
so an export doesn't carry deleted items that only another hold keeps.

The finished file is a blob of whoever started the export, so only they
download it, and it lasts as long as any upload (uploadTtl). Exports
are records under the hold (SUBSPACE_INBUXA H/e): never changed or
destroyed, each with its status, counts, size and checksum. Starting
one needs sysLegalHoldExport, an active hold and a reason, and is
recorded in the audit log like the audit log's own export.

The build is in memory and capped at 2 GB; bigger holds fail with a
message saying so, and are split by picking accounts.

Tested: unit tests for safe ZIP names and the manifest and its hash;
the legal_hold system test, on RocksDB, PostgreSQL and MySQL, exports a
hold end to end (live and archived mail, the manifest's hash, an asked-
for account the hold doesn't cover left out) and checks the refusals
(no reason, a user without the permission, a released hold) and the
audit record; and by hand from the console on a local server. Not
covered by a test: the archived-item date range with two holds of
different ranges over one account.

tests/Cargo.toml

@@ -86,6 +86,7 @@ dns-update = { version = "0.5", features = ["test_provider"] }
 x509-parser = "0.18"
 rcgen = "0.14"
 sha2 = "0.11"
+zip = "8.6" # inbuxa: reading legal hold exports
 time = "0.3"
 testcontainers = { version = "0.28", features = ["reusable-containers"] }
 rust-s3 = { version = "0.37", default-features = false, features = ["tokio-rustls-tls"] }

tests/src/system/legal_hold.rs

@@ -436,6 +436,90 @@ pub async fn test(test: &mut TestServer) {
     names.sort_unstable();
     assert_eq!(names, vec!["Matter 7001", "Matter 7002"], "LH-14: {response}");
 
+    // LH-12: collect what the hold keeps, as a ZIP with its manifest
+    import(&frozen_client, "Still in the inbox", None).await;
+    let (_, response) = admin
+        .hold_call(
+            "inbuxa:HoldExport/set",
+            json!({"create": {"x": {"holdId": first, "accountIds": [frozen.id_string()]}}}),
+        )
+        .await;
+    assert_eq!(
+        response["notCreated"]["x"]["type"], "invalidProperties",
+        "AU-12: an export without a reason: {response}"
+    );
+    let (_, response) = admin
+        .hold_call(
+            "inbuxa:HoldExport/set",
+            json!({"reason": "Production to opposing counsel",
+                "create": {"x": {"holdId": first,
+                    "accountIds": [frozen.id_string(), admin.id_string()]}}}),
+        )
+        .await;
+    let export_id = response["created"]["x"]["id"]
+        .as_str()
+        .unwrap_or_else(|| panic!("LH-12: not started: {response}"))
+        .to_string();
+    let mut export = Value::Null;
+    for _ in 0..60 {
+        let (_, got) = admin
+            .hold_call("inbuxa:HoldExport/get", json!({"ids": [export_id]}))
+            .await;
+        export = got["list"][0].clone();
+        if export["status"] != "running" {
+            break;
+        }
+        tokio::time::sleep(std::time::Duration::from_millis(250)).await;
+    }
+    assert_eq!(export["status"], "ready", "LH-12: {export}");
+    let bytes = admin
+        .jmap_client()
+        .await
+        .download(export["blobId"].as_str().unwrap())
+        .await
+        .unwrap();
+    assert_eq!(export["size"].as_u64(), Some(bytes.len() as u64), "{export}");
+    let mut zip = zip::ZipArchive::new(std::io::Cursor::new(bytes)).unwrap();
+    let names = (0..zip.len())
+        .map(|i| zip.by_index(i).unwrap().name().to_string())
+        .collect::<Vec<_>>();
+    assert!(
+        names.iter().any(|n| n.starts_with("[email protected]/mail/") && n.ends_with(".eml")),
+        "LH-12: live mail missing: {names:?}"
+    );
+    assert!(
+        names.iter().any(|n| n.starts_with("[email protected]/archived/email/")),
+        "LH-12: the kept deleted mail is missing: {names:?}"
+    );
+    assert!(
+        names
+            .iter()
+            .all(|n| n.starts_with("[email protected]/") || n.starts_with("manifest.")),
+        "LH-12: an account the hold doesn't cover was exported: {names:?}"
+    );
+    let mut manifest = String::new();
+    std::io::Read::read_to_string(&mut zip.by_name("manifest.csv").unwrap(), &mut manifest).unwrap();
+    let mut hash = String::new();
+    std::io::Read::read_to_string(&mut zip.by_name("manifest.sha256").unwrap(), &mut hash).unwrap();
+    use sha2::Digest;
+    let expected: String = sha2::Sha256::digest(manifest.as_bytes())
+        .iter()
+        .map(|b| format!("{b:02x}"))
+        .collect();
+    assert!(hash.starts_with(&expected), "LH-12: the manifest's hash doesn't match");
+    assert!(manifest.contains(",true,"), "LH-12: nothing marked archived: {manifest}");
+    // LH-13: only sysLegalHoldExport starts one
+    let (_, response) = frozen
+        .hold_call(
+            "inbuxa:HoldExport/set",
+            json!({"reason": "Mine", "create": {"x": {"holdId": first}}}),
+        )
+        .await;
+    assert!(
+        response.to_string().contains("forbidden") && response["created"].is_null(),
+        "LH-13: a user exported a hold: {response}"
+    );
+
     let (_, response) = frozen
         .hold_call("x:ArchivedItem/set", json!({"destroy": [item_id]}))
         .await;
@@ -470,6 +554,16 @@ pub async fn test(test: &mut TestServer) {
         .await;
     let item = archived(frozen.archived_items().await);
     assert!(!is_held(&item), "LH-10: the last release left it held: {item}");
+    let (_, response) = admin
+        .hold_call(
+            "inbuxa:HoldExport/set",
+            json!({"reason": "Too late", "create": {"x": {"holdId": first}}}),
+        )
+        .await;
+    assert_eq!(
+        response["notCreated"]["x"]["type"], "invalidProperties",
+        "LH-12: a released hold was exported: {response}"
+    );
     let until = item["archivedUntil"].as_str().unwrap_or_default().to_string();
     let grace = chrono::Utc::now() + chrono::Duration::days(29);
     assert!(
@@ -574,6 +668,22 @@ pub async fn test(test: &mut TestServer) {
     for reason in ["Counsel's letter", "Counsel widened the matter", "Matter settled"] {
         assert!(reasons.contains(&reason), "AU-12: {reason:?} not recorded: {reasons:?}");
     }
+    // AU-1.9: an export is recorded with its reason
+    let (_, query) = admin
+        .hold_call(
+            "inbuxa:AuditEvent/query",
+            json!({"filter": {"targetKind": "inbuxa:HoldExport"}}),
+        )
+        .await;
+    let (_, exports) = admin
+        .hold_call("inbuxa:AuditEvent/get", json!({"ids": query["ids"].clone()}))
+        .await;
+    assert!(
+        exports["list"]
+            .as_array()
+            .is_some_and(|l| l.iter().any(|r| r["reason"] == "Production to opposing counsel")),
+        "AU-1.9: the export isn't recorded: {exports}"
+    );
     // A release is recorded under the hold's name, from before to after
     let list = records["list"].as_array().cloned().unwrap_or_default();
     let release = list